© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11612
    Prev
    Next
    INDEX
    Explanations

    things that relate to vendors, places, and things for sale in a game

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.60
    ########.
    -0.56
     Reverso
    -0.55
    TagHelpers
    -0.49
    \}_{
    -0.48
     vicin
    -0.48
    المكان
    -0.47
     NSCoder
    -0.47
     externi
    -0.46
     universitaire
    -0.46
    POSITIVE LOGITS
    IntoConstraints
    0.63
    CloseOperation
    0.62
    WebServlet
    0.60
     InputDecoration
    0.60
    anthene
    0.55
     referenties
    0.53
    titleMargin
    0.52
    ManagedBean
    0.52
    FLOR
    0.52
    ibrator
    0.52
    Activations Density 1.259%

    No Known Activations